Search Results for author:
Found 188 papers, 79 papers with code
Augmenting Topic Aware Knowledge-Grounded Conversations with Dynamic Built Knowledge Graphs
Dialog topic management and background knowledge selection are essential factors for the success of knowledge-grounded open-domain conversations.
Improving Constituent Representation with Hypertree Neural Networks
Many natural language processing tasks involve text spans and thus high-quality span representations are needed to enhance neural approaches to these tasks.
Dispersed EM-VAEs for Interpretable Text Generation
Interpretability is important in text generation for guiding the generation with interpretable attributes.
GLAT: Glancing at Latent Variables for Parallel Text Generation
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning
Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'.
Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
Evaluated across a range of both masked and autoregressive LMs on benchmark GLUE tasks, MeZO-SVRG outperforms MeZO with up to 20% increase in test accuracies in both full- and partial-parameter fine-tuning settings.
HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks.
Ranked #70 on
Visual Question Answering
on MM-Vet
Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks
Advanced generative model (e. g., diffusion model) derived from simplified continuity assumptions of data distribution, though showing promising progress, has been difficult to apply directly to geometry generation applications due to the multi-modality and noise-sensitive nature of molecule geometry.
DeepCRE: Transforming Drug R&D via AI-Driven Cross-drug Response Evaluation
The fields of therapeutic application and drug research and development (R&D) both face substantial challenges, i. e., the therapeutic domain calls for more treatment alternatives, while numerous promising pre-clinical drugs have failed in clinical trials.
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Agents share Q-value network periodically during the training process.
Multi-Scale Protein Language Model for Unified Molecular Modeling
Protein language models have demonstrated significant potential in the field of protein engineering.
A Review of Data Mining in Personalized Education: Current Trends and Future Prospects
Personalized education, tailored to individual student needs, leverages educational technology and artificial intelligence (AI) in the digital age to enhance learning effectiveness.
Structure-Based Drug Design via 3D Molecular Generative Pre-training and Sampling
We develop a novel 3D graph editing model to generate molecules using fragments, and pre-train this model on abundant 3D ligands for learning target-independent properties.
VideoPrism: A Foundational Visual Encoder for Video Understanding
We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model.
A monotone piecewise constant control integration approach for the two-factor uncertain volatility model
Numerical results show remarkable agreement with benchmark solutions obtained by unconditionally monotone finite differences, tree methods, and Monte Carlo simulation, underscoring the robustness and effectiveness of our method.
FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition
To address these issues, FROSTER employs a residual feature distillation approach to ensure that CLIP retains its generalization capability while effectively adapting to the action recognition task.
Multi-fidelity physics constrained neural networks for dynamical systems
As a result, during the training of predictive models, physical constraints can be evaluated within low-fidelity spaces, yielding a trade-off between training efficiency and accuracy.
Revisiting the Markov Property for Machine Translation
In this paper, we re-examine the Markov property in the context of neural machine translation.
On Prompt-Driven Safeguarding for Large Language Models
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) from complying with queries that contain harmful intents.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
Equivariant Flow Matching with Hybrid Probability Transport
The generation of 3D molecules requires simultaneously deciding the categorical features~(atom types) and continuous features~(atom coordinates).
RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation
Our key innovation is to develop a multi-stage diffusion process.
Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer
Active Domain Adaptation (ADA) aims to maximally boost model adaptation in a new target domain by actively selecting a limited number of target data to annotate. This setting neglects the more practical scenario where training data are collected from multiple sources.
RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge
Therefore, to evaluate the ability of LLMs to discern the reliability of external knowledge, we create a benchmark from existing knowledge bases.
Rethinking Evaluation Metrics of Open-Vocabulary Segmentaion
We benchmarked the proposed evaluation metrics on 12 open-vocabulary methods of three segmentation tasks.
Large Language Models Are Not Robust Multiple Choice Selectors
This work shows that modern LLMs are vulnerable to option position changes in MCQs due to their inherent "selection bias", namely, they prefer to select specific option IDs as answers (like "Option A").
TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching
Local feature matching remains a challenging task, primarily due to difficulties in matching sparse keypoints and low-texture regions.
Sign Language Translation with Iterative Prototype
Technically, IP-SLT consists of feature extraction, prototype initialization, and iterative prototype refinement.
Ranked #5 on
Sign Language Translation
on CSL-Daily
A Multilayer Perceptron-based Fast Sunlight Assessment for the Conceptual Design of Residential Neighborhoods under Chinese Policy
This requirement is a prerequisite for obtaining a building permit during the conceptual design of a residential project.
Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs.
Multimodal Molecular Pretraining via Modality Blending
Self-supervised learning has recently gained growing interest in molecular modeling for scientific tasks such as AI-assisted drug discovery.
VideoGLUE: Video General Understanding Evaluation of Foundation Models
We evaluate existing foundation models video understanding capabilities using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition, temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring a foundation model (FM) for a downstream task.
INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classification
It uses granular balls to simulate the spatial distribution characteristics of datasets, and informed entropy is utilized to further optimize the granular-ball space.
Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions
Secondly, we find that LLMs' ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages.
Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks.
Non-Autoregressive Document-Level Machine Translation
However, current NAT models still have a significant performance gap compared to their AT counterparts.
Smart Home Energy Management: VAE-GAN synthetic dataset generator and Q-learning
In this paper, we propose a novel variational auto-encoder-generative adversarial network (VAE-GAN) technique for generating time-series data on energy consumption in smart homes.
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
To settle this issue, we propose the Fine-purifying approach, which utilizes the diffusion theory to study the dynamic process of fine-tuning for finding potentially poisonous dimensions.
HIORE: Leveraging High-order Interactions for Unified Entity Relation Extraction
Entity relation extraction consists of two sub-tasks: entity recognition and relation extraction.
Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
Generating desirable molecular structures in 3D is a fundamental problem for drug discovery.
Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training
However, the pre-trained dialogue model's ability to utilize long-range context is limited due to the scarcity of long-turn dialogue sessions.
Cooperative Hierarchical Deep Reinforcement Learning based Joint Sleep, Power, and RIS Control for Energy-Efficient HetNet
In this work, we jointly consider sleep and transmission power control for reconfigurable intelligent surface (RIS)-aided energy-efficient heterogeneous networks (Hetnets).
Learning Harmonic Molecular Representations on Riemannian Manifold
In this work, we propose a Harmonic Molecular Representation learning (HMR) framework, which represents a molecule using the Laplace-Beltrami eigenfunctions of its molecular surface.
A Survey on Model-based, Heuristic, and Machine Learning Optimization Approaches in RIS-aided Wireless Networks
Model-based, heuristic, and ML approaches are compared in terms of stability, robustness, optimality and so on, providing a systematic understanding of these techniques.
Towards Diverse Temporal Grounding under Single Positive Labels
In this study, we reformulate this task as a one-vs-many optimization problem under the condition of single positive labels.
Beam Selection for Energy-Efficient mmWave Network Using Advantage Actor Critic Learning
Compared to the ESB and fixed transmission power strategy, the proposed approach achieves more than twice the average EE in the scenarios under test and is closer to the maximum theoretical EE.
Cross-modal information fusion for voice spoofing detection
Researchers have proposed many methods to defend against these attacks, but in the existing methods, researchers just focus on speech features.
Ranked #1 on
Voice Anti-spoofing
on ASVspoof 2019 - PA
On Pre-trained Language Models for Antibody
The development of general protein and antibody-specific pre-trained language models both facilitate antibody prediction tasks.
Graph Contrastive Learning for Skeleton-based Action Recognition
In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences.
Ranked #9 on
Skeleton Based Action Recognition
on NTU RGB+D
Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning
Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner.
Hierarchical Reinforcement Learning for RIS-Assisted Energy-Efficient RAN
Reconfigurable intelligent surface (RIS) is emerging as a promising technology to boost the energy efficiency (EE) of 5G beyond and 6G networks.
Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning
Previously, non-autoregressive models were widely perceived as being superior in generation efficiency but inferior in generation quality due to the difficulties of modeling multiple target modalities.
Accelerating Antimicrobial Peptide Discovery with Latent Structure
By sampling in the latent space, LSSAMP can simultaneously generate peptides with ideal sequence attributes and secondary structures.
Direct Heterogeneous Causal Learning for Resource Allocation Problems in Marketing
Our key intuition is that we introduce the decision factor to establish a bridge between ML and OR such that the solution can be directly obtained in OR by only performing the sorting or comparison operations on the decision factor.
ROSE: Robust Selective Fine-tuning for Pre-trained Language Models
Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks.
Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition
Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis.
PARAGEN : A Parallel Generation Toolkit
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.
IMB-NAS: Neural Architecture Search for Imbalanced Datasets
In this paper, we propose a new and complementary direction for improving performance on long tailed datasets - optimizing the backbone architecture through neural architecture search (NAS).
Towards Regression-Free Neural Networks for Diverse Compute Platforms
With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important.
Fraud Dataset Benchmark and Applications
Standardized datasets and benchmarks have spurred innovations in computer vision, natural language processing, multi-modal and tabular settings.
Manual-Guided Dialogue for Flexible Conversational Agents
Modeling these subtasks is consistent with the human agent's behavior patterns.
Joint Sensing and Communications for Deep Reinforcement Learning-based Beam Management in 6G
Then we propose a UK-medoids based method for user clustering with location uncertainty, and the clustering results are consequently used for the beam management.
On the Learning of Non-Autoregressive Transformers
Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to reduce the decoding latency by predicting the whole sentences in parallel.
Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel.
Enhancing Cross-lingual Transfer by Manifold Mixup
Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances.
Deep Reinforcement Learning-based Radio Resource Allocation and Beam Management under Location Uncertainty in 5G mmWave Networks
In this paper, we propose a UK-means-based clustering and deep reinforcement learning-based resource allocation algorithm (UK-DRL) for radio resource allocation and beam management in 5G mmWave networks.
One-Class Model for Fabric Defect Detection
Our model takes advantage of a well-designed Gabor filter bank to analyze fabric texture.
Contextual Representation Learning beyond Masked Language Modeling
How do masked language models (MLMs) such as BERT learn contextual representations?
$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning
Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR).
Variational Autoencoder Generative Adversarial Network for Synthetic Data Generation in Smart Home
To this end, in this paper, we propose a Variational AutoEncoder Generative Adversarial Network (VAE-GAN) as a smart grid data generative model which is capable of learning various types of data distributions and generating plausible samples from the same distribution without performing any prior analysis on the data before the training phase. We compared the Kullback-Leibler (KL) divergence, maximum mean discrepancy (MMD), and Wasserstein distance between the synthetic data (electrical load and PV production) distribution generated by the proposed model, vanilla GAN network, and the real data distribution, to evaluate the performance of our model.
Unsupervised Editing for Counterfactual Stories
We also propose a new metric to alleviate the shortcomings of current automatic metrics and better evaluate the trade-off.
Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failures
Microgrids (MGs) are important players for the future transactive energy systems where a number of intelligent Internet of Things (IoT) devices interact for energy management in the smart grid.
Learning Logic Rules for Document-level Relation Extraction
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #21 on
Relation Extraction
on DocRED
A Survey on Green Deep Learning
In recent years, larger and deeper models are springing up and continuously pushing state-of-the-art (SOTA) results across various fields like natural language processing (NLP) and computer vision (CV).
Sliding Sequential CVAE with Time Variant Socially-aware Rethinking for Trajectory Prediction
First, with the continuation of time, the prediction error at each time step increases significantly, causing the final displacement error to be impossible to ignore.
CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
In this paper, we present a large-scale Chinese news summarization dataset CNewSum, which consists of 304, 307 documents and human-written summaries for the news feed.
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.
Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
How do we perform efficient inference while retaining high translation quality?
Simulated annealing for optimization of graphs and sequences
The key idea is to integrate powerful neural networks into metaheuristics (e. g., simulated annealing, SA) to restrict the search space in discrete optimization.
Generating Antimicrobial Peptides from Latent Secondary Structure Space
By sampling in the latent secondary structure space, we can generate peptides with ideal amino acids and secondary structures at the same time.
NAIL: A Challenging Benchmark for Na\"ive Logical Reasoning
Logical reasoning over natural text is an important capability towards human level intelligence.
Non-Autoregressive Models are Better Multilingual Translators
Multilingual machine translation aims to develop a single model for multiple language directions.
Knowledge Guided Geometric Editing for Unsupervised Drug Design
Deep learning models have been widely used in automatic drug design.
Smart Home Energy Management: Sequence-to-Sequence Load Forecasting and Q-Learning
A smart home energy management system (HEMS) can contribute towards reducing the energy costs of customers; however, HEMS suffers from uncertainty in both energy generation and consumption patterns.
The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
Learning from Peers: Deep Transfer Reinforcement Learning for Joint Radio and Cache Resource Allocation in 5G RAN Slicing
In this paper, we propose a deep transfer reinforcement learning (DTRL) scheme for joint radio and cache resource allocation to serve 5G RAN slicing.
Physiological-Physical Feature Fusion for Automatic Voice Spoofing Detection
This method involves feature extraction, a densely connected convolutional neural network with squeeze and excitation block (SE-DenseNet), multi-scale residual neural network with squeeze and excitation block (SE-Res2Net) and feature fusion strategies.
MTG: A Benchmark Suite for Multilingual Text Generation
We introduce MTG, a new benchmark suite for training and evaluating multilingual text generation.
Impact of Acceleration/deceleration Limits on the String Stability of Adaptive Cruise Control
This paper demonstrates that the acceleration/deceleration limits in ACC systems can make a string stable ACC amplify the speed perturbation in natural driving.
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.
Follow Your Path: a Progressive Method for Knowledge Distillation
However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima.
UniRE: A Unified Label Space for Entity Relation Extraction
Entities and relations are represented by squares and rectangles in the table.
Probabilistic Graph Reasoning for Natural Proof Generation
In this paper, we propose PRobr, a novel approach for joint answer prediction and proof generation.
Short-Term Load Forecasting for Smart HomeAppliances with Sequence to Sequence Learning
Appliance-level load forecasting plays a critical role in residential energy management, besides having significant importance for ancillary services performed by the utilities.
Improving Sign Language Translation with Monolingual Data by Sign Back-Translation
Finally, the synthetic parallel data serves as a strong supplement for the end-to-end training of the encoder-decoder SLT framework.
Ranked #4 on
Sign Language Translation
on CSL-Daily
Compatibility-aware Heterogeneous Visual Search
Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images.
Fundamental Diagrams of Commercial Adaptive Cruise Control: Worldwide Experimental Evidence
Experimental measurements on commercial adaptive cruise control (ACC) vehicles \RoundTwo{are} becoming increasingly available from around the world, providing an unprecedented opportunity to study the traffic flow characteristics that arise from this technology.
Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
Thus REDER enables reversible machine translation by simply flipping the input and output ends.
Significance of Low-level Controller for String Stability under Adaptive Cruise Control
Current commercial adaptive cruise control (ACC) systems consist of an upper-level planner controller that decides the optimal trajectory that should be followed, and a low-level controller in charge of sending the gas/brake signals to the mechanical system to actually move the vehicle.
ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction
Current state-of-the-art systems for joint entity relation extraction (Luan et al., 2019; Wad-den et al., 2019) usually adopt the multi-task learning framework.
Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding
Meanwhile, modified feature assigned with style-like words (including adjectives, adverbs, etc) represents the subjective information, and thus brings personalized predictions; De-bias - We propose a de-bias mechanism to generate diverse predictions, aim to alleviate the bias caused by single-style annotations in the presence of label uncertainty.
MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Searching for novel molecules with desired chemical properties is crucial in drug discovery.
Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection
Consequently, we address the weakness of IoU by introducing one geometric sensitive search algorithm as a new assignment and regression metric.
Correlated Deep Q-learning based Microgrid Energy Management
Microgrid (MG) energy management is an important part of MG operation.
Decentralized Microgrid Energy Management: A Multi-agent Correlated Q-learning Approach
The EMS of an MG could be rather complicated when renewable energy resources (RER), energy storage system (ESS) and demand side management (DSM) need to be orchestrated.
Triangular Bidword Generation for Sponsored Search Auction
Our proposed model is simple yet effective: by using bidword as the bridge between search query and advertisement, the generation of search query, advertisement and bidword can be jointly learned in the triangular training framework.
Learning from deep model via exploring local targets
However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima.
Information-theoretic Vocabularization via Optimal Transport
In this paper, we find an exciting relation between an information-theoretic feature and the performance of NLP tasks such as machine translation with a given vocabulary.
Adaptive Gradient Methods Can Be Provably Faster than SGD with Random Shuffling
Adaptive gradient methods have been shown to outperform SGD in many tasks of training neural networks.
Non-iterative Parallel Text Generation via Glancing Transformer
Although non-autoregressive models with one-iteration generation achieves remarkable inference speed-up, they still falls behind their autoregressive counterparts inprediction accuracy.
Vocabulary Learning via Optimal Transport for Neural Machine Translation
The choice of token vocabulary affects the performance of machine translation.
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing
Essentially, DGCPN addresses the inaccurate similarity problem by exploring and exploiting the data's intrinsic relationships in a graph.
LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
The final claim verification is based on all latent variables.
Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
i) We generate a bird view map, which is naturally free from occlusion issues, and scan all points on it to look for suitable locations for each pedestrian instance.
Reciprocal Supervised Learning Improves Neural Machine Translation
Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT).
CPM: A Large-scale Generative Chinese Pre-trained Language Model
However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available.
On the Sentence Embeddings from Pre-trained Language Models
Pre-trained contextual representations like BERT have achieved great success in natural language processing.
Ranked #16 on
Semantic Textual Similarity
on STS16
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions
As there is no clean mapping for a user's free form utterance to an ontology, we first model the user preferences as estimated distributions over the system ontology and map the users' utterances to such distributions.
Rethinking Document-level Neural Machine Translation
This paper does not aim at introducing a novel model for document-level neural machine translation.
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs?
Ranked #3 on
Machine Translation
on WMT2014 English-French
(using extra training data)
WeChat Neural Machine Translation Systems for WMT20
We participate in the WMT 2020 shared news translation task on Chinese to English.
"Listen, Understand and Translate": Triple Supervision Decouples End-to-end Speech-to-text Translation
Can we build a system to fully utilize signals in a parallel ST corpus?
Consecutive Decoding for Speech-to-text Translation
The key idea is to generate source transcript and target translation text with a single decoder.
Congested Urban Networks Tend to Be Insensitive to Signal Settings: Implications for Learning-Based Control
Notably, we found that no control (i. e. random policy) can be an effective control strategy for a surprisingly large family of networks.
Glancing Transformer for Non-Autoregressive Neural Machine Translation
With GLM, we develop Glancing Transformer (GLAT) for machine translation.
Ranked #69 on
Machine Translation
on WMT2014 English-German
Generating Fluent Adversarial Examples for Natural Languages
Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge.
Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods
It has been a common approach to pre-train a language model on a large corpus and fine-tune it on task-specific data.
Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation
Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios.
Xiaomingbot: A Multilingual Robot News Reporter
This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence.
Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency.
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
Ideally, this results in images from two domains that present shared information to the primary network.
Ranked #2 on
Monocular Depth Estimation
on Make3D
Network On Network for Tabular Data Classification in Real-world Applications
As a result, the intra-field information and the non-linear interactions between those operations (e. g. neural network and factorization machines) are ignored.
Mirror-Generative Neural Machine Translation
Training neural machine translation models (NMT) requires a large amount of parallel corpus, which is scarce for many language pairs.
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space
We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently.
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations.
Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip
In this paper, motivated by the inherent connections between neural joint source-channel coding and discrete representation learning, we propose a novel regularization method called Infomax Adversarial-Bit-Flip (IABF) to improve the stability and robustness of the neural joint source-channel coding scheme.
MajorityNets: BNNs Utilising Approximate Popcount for Improved Efficiency
Binarized neural networks (BNNs) have shown exciting potential for utilising neural networks in embedded implementations where area, energy and latency constraints are paramount.
Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
Our STMC network consists of a spatial multi-cue (SMC) module and a temporal multi-cue (TMC) module.
Variational Template Machine for Data-to-Text Generation
We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables.
Non-autoregressive Transformer by Position Learning
Non-autoregressive models are promising on various text generation tasks.
Importance-Aware Learning for Neural Headline Editing
We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers.
Visual Relationship Detection with Relative Location Mining
Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently.
Kernelized Bayesian Softmax for Text Generation
Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase.
Review of Learning-based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps between Self-driving and Traffic Congestion
Some suggestions towards congestion mitigation for future mMP studies are proposed: i) enrich data collection to facilitate the congestion learning, ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and iii) integrate domain knowledge from the traditional car following (CF) theory to improve the string stability of mMP.
GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition
In this work, we propose a Global-Local Spherical Harmonics (GLoSH) lighting model to improve the lighting component, and jointly predict reflectance and surface normals.
Deep Single-Image Portrait Relighting
In this work, we apply a physically-based portrait relighting method to generate a large scale, high quality, "in the wild" portrait relighting dataset (DPR).
Ranked #1 on
Single-Image Portrait Relighting
on Multi-PIE
(using extra training data)
Rethinking Text Attribute Transfer: A Lexical Analysis
We apply this framework to existing datasets and models and show that: (1) the pivot words are strong features for the classification of sentence attributes; (2) to change the attribute of a sentence, many datasets only requires to change certain pivot words; (3) consequently, many transfer models only perform the lexical-level modification, while leaving higher-level sentence structures unchanged.
PNAT: Non-autoregressive Transformer by Position Learning
However, position modeling of output words is an essential problem in non-autoregressive text generation.
Unsupervised Paraphrasing by Simulated Annealing
Unsupervised paraphrase generation is a promising and important research topic in natural language processing.
Towards Making the Most of BERT in Neural Machine Translation
Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pre-training aided NMT by 1. 4 BLEU score.
Large-scale traffic signal control using machine learning: some traffic flow considerations
We find that: (i) a policy trained with supervised learning with only two examples outperforms LQF, (ii) random search is able to generate near-optimal policies, (iii) the prevailing average network occupancy during training is the major determinant of the effectiveness of DRL policies.
Correct-and-Memorize: Learning to Translate from Interactive Revisions
Experiments in both ideal and real interactive translation settings demonstrate that our proposed \method enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods.
Generating Sentences from Disentangled Syntactic and Semantic Spaces
In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces.
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
To enhance the controllability and interpretability, one can replace the Gaussian prior with a mixture of Gaussian distributions (GM-VAE), whose mixture components could be related to hidden semantic aspects of data.
Imitation Learning for Non-Autoregressive Neural Machine Translation
Non-autoregressive translation models (NAT) have achieved impressive inference speedup.
Dynamically Fused Graph Network for Multi-hop Reasoning
However, many difficult questions require multiple supporting evidence from scattered text among two or more documents.
Ranked #33 on
Question Answering
on HotpotQA
AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications
Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses.
Domain-Constrained Advertising Keyword Generation
Second, the inefficient ad impression issue: a large proportion of search queries, which are unpopular yet relevant to many ad keywords, have no ads presented on their search result pages.
CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements.
DeepHTTP: Semantics-Structure Model with Attention for Anomalous HTTP Traffic Detection and Pattern Mining
In the Internet age, cyber-attacks occur frequently with complex types.
Transferable Positive/Negative Speech Emotion Recognition via Class-wise Adversarial Domain Adaptation
Speech emotion recognition plays an important role in building more intelligent and human-like agents.
On Tree-Based Neural Sentence Modeling
To study the effectiveness of different tree structures, we replace the parsing trees with trivial trees (i. e., binary balanced tree, left-branching tree and right-branching tree) in the encoders.
Ranked #9 on
Sentiment Analysis
on Amazon Review Full
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation
The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the posterior and prior.
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces
We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image.
BRITS: Bidirectional Recurrent Imputation for Time Series
It is ubiquitous that time series contains many missing values.
General Classification
Multivariate Time Series Forecasting
+5
QA4IE: A Question Answering based Framework for Information Extraction
Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts.
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies?
Modeling Past and Future for Neural Machine Translation
The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents.
Dynamic Oracle for Neural Machine Translation in Decoding Phase
However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it.
Augmenting End-to-End Dialog Systems with Commonsense Knowledge
Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence.
A Deep Cascade Network for Unaligned Face Attribute Classification
First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes.
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image.
Word-Context Character Embeddings for Chinese Word Segmentation
Neural parsers have benefited from automatically labeled data via dependency-context word embeddings.
Chunk-Based Bi-Scale Decoder for Neural Machine Translation
In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN.
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents.
Solving Uncalibrated Photometric Stereo Using Fewer Images by Jointly Optimizing Low-rank Matrix Completion and Integrability
We introduce a new, integrated approach to uncalibrated photometric stereo.
Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease
Consider samples from two different data sources $\{\mathbf{x_s^i}\} \sim P_{\rm source}$ and $\{\mathbf{x_t^i}\} \sim P_{\rm target}$.
Context-aware Natural Language Generation for Spoken Dialogue Systems
Most tranditional QA systems based on templates or rules tend to generate rigid and stylised responses without the natural variation of human language.
Evaluating a Deterministic Shift-Reduce Neural Parser for Constituent Parsing
Greedy transition-based parsers are appealing for their very fast speed, with reasonably high accuracies.
